bool String::Contains(s_char c) const
{
MUTEX_LOCK(str_mutex);
#ifdef SCRATCH_NO_UTF8
int iLen = strlen(str_szBuffer);
for (int i = 0; i < iLen; i++) {
if (str_szBuffer[i] == c) {
return true;
}
}
return false;
#else
return utf8chr(str_szBuffer, c) != nullptr;
#endif
}
RegexRule::RegexRule(string region, string pattern, std::string letters_regex, std::string numbers_regex)
//: re2_regex("")
{
this->original = pattern;
this->region = region;
this->regex = "";
this->valid = false;
string::iterator end_it = utf8::find_invalid(pattern.begin(), pattern.end());
if (end_it != pattern.end()) {
cerr << "Invalid UTF-8 encoding detected " << endl;
return;
}
std::stringstream regexval;
string::iterator utf_iterator = pattern.begin();
numchars = 0;
while (utf_iterator < pattern.end())
{
int cp = utf8::next(utf_iterator, pattern.end());
string utf_character = utf8chr(cp);
if (utf_character == "[")
{
regexval << "[";
while (utf_character != "]" )
{
if (utf_iterator >= pattern.end())
break; // Invalid regex, don't bother processing
int cp = utf8::next(utf_iterator, pattern.end());
utf_character = utf8chr(cp);
regexval << utf_character;
}
}
else if (utf_character == "\\")
{
// Don't add "\" characters to our character count
regexval << utf_character;
continue;
}
else if (utf_character == "?")
{
regexval << ".";
this->skipPositions.push_back(numchars);
}
else if (utf_character == "@")
{
regexval << letters_regex;
}
else if (utf_character == "#")
{
regexval << numbers_regex;
}
else if ((utf_character == "*") || (utf_character == "+"))
{
cerr << "Regex with wildcards (* or +) not supported" << endl;
}
else
{
regexval << utf_character;
}
numchars++;
}
this->regex = regexval.str();
re2_regex = new re2::RE2(this->regex);
if (!re2_regex->ok()) {
cerr << "Unable to load regex: " << pattern << endl;
}
else
{
this->valid = true;
}
}
